Monitoring of Sows’ Standing Reflex During Estrus Based on Machine Vision

Monitoring estrus in sows is crucial for enhancing the efficiency of production management in pig farms. Standing reflex, as a clear sign of estrus and the optimal timing indicator for artificial insemination, has lacked an efficient and reliable method for monitoring. This study developed an approach based on machine vision for the automated detection of standing reflex in multiple sows within stalls. Specifically, a detection strategy was proposed based on the analysis of movement patterns by first calculating the Intersection over Union (IoU) sequence for each sow, followed by classification of standing reflex versus non-standing reflex sequences using a Convolutional–BiLSTM–Attention (CBA) network. Additionally, the lying targets were excluded from sequential classification while employing the improved YOLOv8 for segmentation. A total of 1484 images were captured for instance segmentation, and 445 IoU sequences were extracted from videos for temporal classification. Experimental results showed that misclassification rate of the improved YOLOv8 was 3% in distinguishing between lying and standing postures, indicating its efficiency in identifying these two states. Moreover, the mean average precision (mAP) of segmentation reached 98.2%, with a detection latency of 7.8 ms per image, demonstrating the model’s efficient capability in extracting target contours. The CBA model achieved an accuracy of 96.6 ± 2.7%. The proposed method enabled accurate monitoring of standing reflex in sows, facilitating more precise control over breeding times.